Harvard physicist Matthew Schwartz releases BootLoops, an open-source harness that let Claude produce 36 manuscripts in 18 fields in three months
On Oct 1, 2026 Anthropic published a guest post, "Claude-Shaped Science", by Harvard theoretical physicist Matthew Schwartz (a visiting researcher at Anthropic). He released BootLoops 1.0, an open-source toolkit that sits between a researcher and an LLM so that Claude can do exact quantitative calculations. With it, Schwartz and 19 co-authors produced 36 manuscripts in 18 fields in three months. Schwartz stresses that Claude's results needed expert checking.
Key facts
- Output: 36 manuscripts in 18 fields with 19 co-authors over about three months, picked from ~400 candidate problems (Anthropic guest post)
- Particle physics: 30 integrals computed with the bootstrap method, 15 reproducing known results and 15 never computed before
- Economics (NBER w35782, Schwartz, Isaiah Andrews, Jesse M. Shapiro): the workflow ran 4,452 replication packages from five journals, flagged discrepancies in 3,460 articles or appendices, cut computation time >10x in 496, and proposed extensions in 923
- Other projects: population genetics on 5.7 billion mutation pairs from the 1000 Genomes Project; a word-stress database (AccStack) covering 6,072 languages; every US forest-inventory plot classified by life-history strategy
- BootLoops is owned and maintained by Schwartz; the work was funded by Anthropic but it is 'not an Anthropic project' (bootloops.ai)
- Caveats from Schwartz: Claude 'likes to declare victory too early', and 'done, with one asterisk' often means 'not done at all'; first findings were often 'technically correct but scientifically unremarkable' until domain experts steered them
Science result
- Field
- other / cross-disciplinary quantitative science (particle physics, economics, genetics, ecology, linguistics)
- Problem
- Making LLM agents useful for exact calculations across many sciences
- Result
- Open-source harness; 36 manuscripts in 18 fields in three months, including 15 new bootstrap integrals and a reproduction of 4,452 economics replication packages
- AI system
- Claude
- Human role
- Human-led with AI tools: Schwartz chose 'Claude-shaped' problems and 19 domain co-authors checked and steered the results
- Verification
- Preprints and working papers; expert co-authors; NBER working paper (not peer-reviewed)
- Status
- pending
What happened
Schwartz argues there is an "impedance mismatch" between how scientists work and what LLMs do best, so instead of making Claude imitate a scientist he looked for "Claude-shaped problems": exact, checkable calculations that recur across fields. BootLoops packages the tools and loops for such work. He reports that Claude reproduced one paper's results in about twenty minutes, a calculation that took him weeks to code originally.
Why it matters
It is one of the broadest demonstrations so far of a single researcher using an AI agent to work across many unrelated fields, with code released openly. The economics replication alone (thousands of papers re-run, thousands of discrepancies flagged) could matter for research transparency. Schwartz's warnings about premature "victory" are a useful counterweight to autonomous-science claims.
Changelog
- 2026-10-05: created (from the leads queue: The Decoder, Oct 3)
People
Related events
Sources (5)
- officialAnthropic (guest post by Matthew Schwartz): Claude-Shaped Science
- officialBootLoops: a toolkit for exact quantitative science
- codeBootLoops source code (GitHub)
- paperNBER w35782: An LLM Workflow That Reproduces, Improves, and Extends Published Economics Research (Schwartz, Andrews, Shapiro)
- pressThe Decoder: Open-source BootLoops harness supports AI models in precise scientific calculations (Oct 3)
id: 2026-10-01-bootloops-claude-shaped-science · updated 2026-10-05 · open in the interactive timeline